Deforestation is the replacement of forest by other land use, while degradation is a reduction of long-term canopy cover and/or forest stock. In the Brazilian Amazon, forest degradation mainly results from selective logging of intact/unmanaged forests and uncontrolled fires. While the contribution of deforestation to carbon emissions is well-known, determining the impact of forest degradation remains challenging. This work presents a semi-automated procedure for classifying forest degradation in Mato Grosso State using fraction images derived from the Linear Spectral Mixing Model (LSMM). Sentinel-2 MSI and Landsat OLI images acquired in 2023 over the study area were selected to develop the proposed method. Discrimination against logging from fires, which produce different levels of forest damage, is important for the UNFCCC (United Nations Framework Convention on Climate Change) REDD+ (Reducing Emissions from Deforestation and Forest Degradation) program.

Amazon is recognized for its biodiversity and has a crucial role in the global climate balance. However, it is currently facing drought, one of the most pressing challenges in its history. Then the objective of this study was to estimate the extent of water coverage in the Amazon biome during the seasonal pulses of rising and descending waters. For this, we used NPP VIIRS and Sentinel-2 MSI mosaics which were acquired during the 2023 peak flood and the peak drought events ever recorded in the Rio Negro, Amazonas. To classify water coverage using images from both sensors, a script was developed in GEE, which applies the Linear Spectral Mixing Model (LSMM). The estimated areas were: 109,169.00 km2(January to July 2023) and 61,477.50 km2(August to October). The drought event in Amazon this year is due to the 2023 strong El Niño and the temperature increase in the North Atlantic.

This article presents a new method for monitoring forest cover in the state of Rondônia, in the Brazilian Amazon. The proposed method applies the Linear Spectral Mixing Model (LSMM) to Landsat datasets (MSS, TM and OLI) to derive annual vegetation, soil, and shade fraction images for the period 1980 – 2020. These fraction images have the advantages of reducing the volume of data to be analyzed and highlighting the target characteristics. Then, we applied a threshold method to classify forest, non-forest, hydrography, and deforestation areas. The proposed method showed to be consistent and flexible allowing to change the threshold values according to the fraction images to obtain the results with high accuracy. The results obtained by the proposed method can be easily checked over the RGB image mosaic. This kind of information is very important for environmental and climate change studies and for supporting government conservation efforts.

This article presents a land use and land cover (LULC) classification map based on Random Forest (RF) classifier algorithm in the São Paulo State (Brazil), using Landsat-8 OLI data. The method consists in using time series images from January to December of 2020 based on the spectral and temporal characteristics of the LULC classes. We performed the classification class by class considering: water, urban area, forest, agriculture, forest plantation and pasture. Then, we pre-processed the selected images based on the spectral characteristics of the targets to highlight each LULC class. After that, the classification was performed using RF for each class individually and then we composed the final map with all LULC classes. The results showed a global accuracy of 89.10%, kappa value of 0.8692, producer accuracies greater than 79.80% and user accuracies greater than 76.82% for the classes mapped. Therefore, the method is consistent allowing to minimize the classification errors facilitating the pos-classification edition of individual classes mapped.

This article presents a method to map the extent of forest plantation in an area located in the São Paulo State (Brazil). The proposed method applies the Linear Spectral Mixing Model (LSMM) to Landsat Thematic Mapper (TM) datasets to derive annually vegetation, soil and shade fraction images for local analysis. We used 30 m annual mosaics of TM images during the 1985 to 1995 time period. These fraction images have the advantage to reduce the volume of data to be analyzed highlighting the target characteristics. Then, we generated only one mosaic for each fraction images for TM dataset computing de maximum value through this period, facilitating the classification of areas occupied by forest plantation. The proposed method allowed to classify two forest plantation classes: Eucalypt and Pine. In addition, it allowed to monitor the phenological stages of Eucalypt according to its growth cycle. The results are very important for planning and management by the commercial companies and can contribute to develop an automatic method to map forest plantation areas in a regional and global scales.

This article presents a land use and land cover (LULC) classification map using Random Forest algorithm in the São Paulo State (Brazil), and an assessment of burned areas using two products (MCD64A1 and MapBiomas Fire). The method uses Landsat Operational Land Imager (OLI) time series images from January to December of 2020. We performed the classification class by class considering: water, urban area, forest formation, sugarcane, agriculture, forest plantation and pasture. For each class, we used different spectral bands and image fraction according to the best response for the class. For 2020, the top three areas mapped in São Paulo State were pasture (40.49%), sugarcane (24.74%) and forest formation (20.60%). Comparing the two burned area products, MCD64A1 mapped more burned areas as it uses MODIS images combined with 1 km active fire observations with higher temporal resolution than MapBiomas Fire. About 60% of the burned areas mapped in 2020 occurred in the sugarcane class. The results show the importance of land use and land cover classification for better understanding fire-prone classes given the spatial distribution. It turns as an environmental tool for environmental strategies of planning and monitoring burned area assessment over regional scales.